Search Results for author: Leslie Kaelbling

Found 10 papers, 1 papers with code

Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning

no code implementations28 Sep 2024 Alicia Li, Nishanth Kumar, Tomás Lozano-Pérez, Leslie Kaelbling

We introduce a simple formulation for such learning, where the RL problem is constructed with a special ``CallPlanner'' action that terminates the bridge policy and hands control of the agent back to the planner.

Reinforcement Learning (RL)

Compositional Generative Modeling: A Single Model is Not All You Need

no code implementations2 Feb 2024 Yilun Du, Leslie Kaelbling

Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research.

Video Language Planning

no code implementations16 Oct 2023 Yilun Du, Mengjiao Yang, Pete Florence, Fei Xia, Ayzaan Wahid, Brian Ichter, Pierre Sermanet, Tianhe Yu, Pieter Abbeel, Joshua B. Tenenbaum, Leslie Kaelbling, Andy Zeng, Jonathan Tompson

We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data.

Learning Interactive Real-World Simulators

no code implementations9 Oct 2023 Sherry Yang, Yilun Du, Kamyar Ghasemipour, Jonathan Tompson, Leslie Kaelbling, Dale Schuurmans, Pieter Abbeel

Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world.

Video Captioning

Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning

no code implementations3 Nov 2022 Zhutian Yang, Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Kaelbling, Dieter Fox

The core of our algorithm is PIGINet, a novel Transformer-based learning method that takes in a task plan, the goal, and the initial state, and predicts the probability of finding motion trajectories associated with the task plan.

Motion Planning Task and Motion Planning +1

Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization

no code implementations NeurIPS 2021 Clement Gehring, Kenji Kawaguchi, Jiaoyang Huang, Leslie Kaelbling

Estimating the per-state expected cumulative rewards is a critical aspect of reinforcement learning approaches, however the experience is obtained, but standard deep neural-network function-approximation methods are often inefficient in this setting.

Model-based Reinforcement Learning reinforcement-learning +1

Active Learning of Abstract Plan Feasibility

no code implementations1 Jul 2021 Michael Noseworthy, Caris Moses, Isaiah Brand, Sebastian Castro, Leslie Kaelbling, Tomás Lozano-Pérez, Nicholas Roy

Long horizon sequential manipulation tasks are effectively addressed hierarchically: at a high level of abstraction the planner searches over abstract action sequences, and when a plan is found, lower level motion plans are generated.

Active Learning

Learning Object-Based State Estimators for Household Robots

no code implementations6 Nov 2020 Yilun Du, Tomas Lozano-Perez, Leslie Kaelbling

The robot may be called upon later to retrieve objects and will need a long-term object-based memory in order to know how to find them.

Clustering Object +2

Residual Policy Learning

1 code implementation15 Dec 2018 Tom Silver, Kelsey Allen, Josh Tenenbaum, Leslie Kaelbling

In these tasks, reinforcement learning from scratch remains data-inefficient or intractable, but learning a residual on top of the initial controller can yield substantial improvements.

Deep Reinforcement Learning reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.